Drafting AI – Human-in-the-loop AI automation for ops teams' email
Hi HN, I'm Jared from Drafting AI (https://getdrafting.com/). We're a Chrome extension that helps operations and customer support teams work through their inboxes more efficiently. Here's a quick demo video: https://www.youtube.com/watch?v=PCDqAMaYx2Q We believe AI can be deployed more widely when you mitigate hallucinations through human-in-the-loop review. This led to two decisions: 1. A Chrome Extension is ideal for presenting actions in third-party apps for human review. When AI suggests issuing a refund via Shopify, what better way to show it than through…
In plain words
Drafting AI is a Chrome extension designed for operations and customer support teams to process emails more efficiently. The tool uses AI to suggest actions like issuing refunds or drafting responses, but requires human review before execution. Rather than automatically performing tasks, it prepares draft actions within third-party applications like Shopify, allowing users to approve, modify, or reject suggestions before completion. This human-in-the-loop approach aims to reduce AI errors while maintaining user control over operations.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I'm Jared from Drafting AI (https://getdrafting.com/). We're a Chrome extension that helps operations and customer support teams work through their inboxes more efficiently. Here's a quick demo video: https://www.youtube.com/watch?v=PCDqAMaYx2Q We believe AI can be deployed more widely when you mitigate hallucinations through human-in-the-loop review. This led to two decisions: 1. A Chrome Extension is ideal for presenting actions in third-party apps for human review. When AI suggests issuing a refund via Shopify, what better way to show it than through Shopify's own refund interface? 2. AI should "draft" responses but not submit them. For instance, it’ll open Shopify admin and fill in refund details, but won't click "submit." This gives the user full control to approve, modify, or discard the AI's suggestions. We believe this "drafting" UX of pre-filling form fields will become standard for AI. It feels like GitHub Copilot's autocomplete UX, but for forms. You can add Drafting (https://getdrafting.com/) to your internal tools today to speed up email-based workflows. It's perfect for any process that follows the pattern of: 1) read email, 2) use internal tool to handle it, 3) reply to email. For an example, consider a customer support rep for an e-commerce. A customer emails about poor product quality. The CS team has configured Drafting AI to process refunds through Shopify for serious quality complaints. The rep opens the email in Gmail or Front and clicks the Drafting AI button. A window appears with Shopify's refund form already filled out, plus a reply draft ready in their email. After reviewing both, they approve and send. We’ve seen that without Drafting AI, a rep can spend 5 minutes just writing the reply email; half their time on a 10 minute ticket. With Drafting AI, reviewing and approving takes seconds. Other use cases include: freight and logistics ops (TMS) coordinating with carriers, travel agents making trip adjustments (GDS), and HR teams processing payroll and benefits requests (HRIS). These and other job roles can sometimes be thought of as using a person as a bridge between email and internal tools. As a Chrome extension, we integrate with all your existing internal tools as long as they’re web-based, whether they’re SaaS (Shopify, Salesforce), nocode/lowcode (Retool, Airtable), or custom apps (React, Rails, Django) Try it at https://getdrafting.com/ or reply here with questions! I'm happy to personally onboard the first 20 teams that reach out.
Does a similar job
all alternatives →
Google Chrome SkillsApr 2026 · blog.google · ▲273Turn your best AI prompts into one-click tools in Chrome
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, November 2024
the whole month →
- IB
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
